Can a convex function be uniformly approximated by convex combination of simpler convex functions?

285 Views Asked by At

According to universal approximation theorem, any continuous function can be uniformly approximated by neural network with single hidden layer.

Similarly, can a convex function $f: \mathbb{R}^n \rightarrow \mathbb{R}$ be uniformly approximated by convex combination of simpler convex functions?

Or, is there any analysis on the collection of convex functions?